Push Reinforce agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Pixelcopter-PLE-v0
+- CartPole-v1
 - reinforce
 - reinforcement-learning
 - custom-implementation
@@ -10,14 +10,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 16.50 +/- 11.73
+      value: 28.20 +/- 6.68
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Pixelcopter-PLE-v0
-      type: Pixelcopter-PLE-v0
+      name: CartPole-v1
+      type: CartPole-v1
 ---
 
   # **Reinforce** Agent playing **CartPole-v1**

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4736534d1f0f19ab1159a2f6565803855712a8a2ce8023ad18c8a7183f48ec2
-size 4703
+oid sha256:3d811ceea47867acd512e669053bf34b8d76106a80cb260b5e7759a4e997dd17
+size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2963f3a3138aa0f23de7497714bb9451393686f2df56a3cf1fc6c5c2f7fdf584
-size 6040
+oid sha256:2c95e33139ed271e8b679420b6e5b820e61a477967e431123c16cad0617af5cd
+size 4954

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.5, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-08T11:25:28.481652"}
+{"env_id": "CartPole-v1", "mean_reward": 28.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-09T11:26:06.263333"}